© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 4970
    Prev
    Next
    INDEX
    Explanations

    specific projects and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ungdom
    1.30
     kiedy
    1.30
    issä
    1.29
     Efter
    1.26
     szer
    1.24
     yıll
    1.21
     sejak
    1.21
    鈮
    1.20
     Entsche
    1.19
    ㄽ
    1.19
    POSITIVE LOGITS
     instrumental
    1.01
    ها
    0.97
     testimonials
    0.95
     extremity
    0.95
     ativos
    0.94
    ים
    0.92
    ter
    0.91
    过程
    0.91
    ა
    0.90
    ๆ
    0.90
    Activations Density 0.000%

    No Known Activations